© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 56276
    Prev
    Next
    INDEX
    Explanations

    terms related to geological processes and transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ«ãĥĪ
    -0.07
     geçir
    -0.07
    å¡ļ
    -0.07
    hai
    -0.06
    erv
    -0.06
     Serg
    -0.06
    ych
    -0.06
    etsk
    -0.06
    OUCH
    -0.06
    ãĥĨãĥ«
    -0.06
    POSITIVE LOGITS
     itself
    0.08
     become
    0.07
     samo
    0.07
     Ñģамо
    0.07
     becoming
    0.07
     becomes
    0.06
    Äĩe
    0.06
     became
    0.06
    ordo
    0.06
    ÑĥÑĢе
    0.06
    Activations Density 0.043%

    No Known Activations